Sistem Inspeksi Cacat pada Permukaan Kayu menggunakan Model Deteksi Obyek YOLOv5
نویسندگان
چکیده
ABSTRAKPermukaan kayu mengalami berbagai serangan serangga dan jamur, sehingga dapat menyebabkan cacat seperti pembusukan pada yang berpengaruh terhadap kualitas harga jual tersebut. Pengujian secara lapangan dengan penglihatan manusia menjadi kurang efektif, karena menghasilkan penilaian subjektif memerlukan waktu lama. Penelitian ini mengusulkan sistem deteksi permukaan pinus karet menggunakan Convolutional Neural Network (CNN) model YOLOv5. dilakukan beberapa dari YOLOv5, serta dua teknik image enhancement, yaitu edge filter Real ESRGAN. Hasil mAP terbaik sebesar 94,3% kecepatan 125 FPS dataset YOLOv5s tanpa penambahan enhancement. Sedangkan memiliki jenis lebih kompleks, hasil adalah 94,7% 139 YOLOv5s-Transformer enhancement ESRGAN.Kata kunci: deteksi, kayu, (CNN), YOLO ABSTRACTWood surafce is subject to various insect and fungal attacks, which can cause defects such as wood rot. This condition affects the quality well selling price of wood. Field testing with human eyesight becomes less effective because it produces a subjective assessment time consuming. study proposes defect detection system on surface pine rubber using YOLOv5 model. System was carried out several models from two techniques, namely The best results were 94.3%, speed without adding While more complex problem, 94.7% addition ESRGAN.Keywords: detection, wood,
منابع مشابه
Sistem Informasi Pengarsipan Menggunakan Algoritma Levensthein String pada Kecamatan Seberang Ulu II
Archival information systems in government agency is one of the most used applications for daily acitivities. One feature in application management information document is searching. This feature serves to search for documents from a collection of available information based on keywords entered by the user. But some researches on a search engine (searching) concluded that the average user error...
متن کاملMultidimensi Pada Data Warehouse Dengan Menggunakan Rumus Kombinasi
Multidimensional in data warehouse is a compulsion and become the most important for information delivery, without multidimensional data warehouse is incomplete. Multidimensional give the able to analyze business measurement in many different ways. Multidimensional is also synonymous with online analytical processing (OLAP).
متن کاملValidasi data dengan menggunakan objek lookup pada borland delphi 7.0
s: Developing an application with some tables must concern the validation of input (scpecially in Table Child). In order to maximize the accuracy and input data validation. Its called lookup (took data from other dataset). There are 2 (two) ways to lookup data from Table Parent: 1) Using Objects (DBLookupComboBox & DBLookupListBox), or 2) Arranging The Properties Of Fields Data Type (shown by u...
متن کاملDesain dan Implementasi Face Recognition dan Live Streaming pada Sistem Digital Assistant untuk Staf Medik Fungsional menggunakan Google Glass
Abstrak— Dalam era globalisasi saat ini, rumah sakit dituntut untuk meningkatkan kinerja dan daya saing sebagai badan usaha dengan tidak mengurangi misi sosial yang dibawanya. Hal ini berarti bahwa rumah sakit harus menerapkan kebijakankebijakan strategis agar mampu secara cepat dan tepat dalam pengambilan keputusan sehingga dapat menjadi organisasi yang responsif, inovatif, efektif, dan efisie...
متن کاملImplementasi Sistem Pengelolaan Proses Bisnis Mengacu Pada Mit Process Handbook
MIT Process Handbook offers a method of storage and retrieval of an organization's business processes. Business community or college students who take the topic of business processes can learn best-practice business processes contained in the MIT Process Handbook. Collection of business processes that are contained in the MIT Process Handbook only manage the business process description in text...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Elkomika
سال: 2022
ISSN: ['2338-8323', '2459-9638']
DOI: https://doi.org/10.26760/elkomika.v10i4.990